README.md

---
tags:
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
- text-to-image
- diffusers
- lora
- template:sd-lora
widget:
- text: a sticker of a smiling emoticion with hands up in the style of <s0><s1>
  output:
    url: image-0.png
- text: a smiley face with hands up in front of a rainbow background in the style
    of <s0><s1>
  output:
    url: image-1.png
- text: a yellow smiley with a paintbrush and paint in the style of <s0><s1>
  output:
    url: image-2.png
- text: a yellow emoticion with a magnifying glass in the style of <s0><s1>
  output:
    url: image-3.png
- text: a yellow sun with a thermometer in its hand in the style of <s0><s1>
  output:
    url: image-4.png
- text: a yellow smiley with a hat and a red heart in the style of <s0><s1>
  output:
    url: image-5.png
- text: a smiley face with a computer chip in the style of <s0><s1>
  output:
    url: image-6.png
- text: world map sticker - 1 in the style of <s0><s1>
  output:
    url: image-7.png
- text: two yellow smiley faces with thumbs up in the style of <s0><s1>
  output:
    url: image-8.png
- text: a yellow smiley face with a hand up in the style of <s0><s1>
  output:
    url: image-9.png
- text: a cartoon character watering a plant with a watering can in the style of <s0><s1>
  output:
    url: image-10.png
- text: a yellow sun with a thermometer and a blue crystal in the style of <s0><s1>
  output:
    url: image-11.png
- text: a yellow sun is holding a drink machine in the style of <s0><s1>
  output:
    url: image-12.png
- text: checklist emoji sticker in the style of <s0><s1>
  output:
    url: image-13.png
- text: a yellow smiley with a paper and a pencil in the style of <s0><s1>
  output:
    url: image-14.png
- text: a yellow smiley face with a rocket on top in the style of <s0><s1>
  output:
    url: image-15.png
- text: a cartoon character with a red eye and a red light in the style of <s0><s1>
  output:
    url: image-16.png
- text: a cartoon character playing the violin in the style of <s0><s1>
  output:
    url: image-17.png
- text: a yellow smiley face with text that says task language license in the style
    of <s0><s1>
  output:
    url: image-18.png
- text: a yellow emoticion with a graduation cap and a pen in the style of <s0><s1>
  output:
    url: image-19.png
- text: a yellow smiley face with a remote control in the style of <s0><s1>
  output:
    url: image-20.png
- text: a yellow smiley face with a colorful letter d in the style of <s0><s1>
  output:
    url: image-21.png
- text: a yellow smiley face with a dragon hat in the style of <s0><s1>
  output:
    url: image-22.png
- text: a yellow smiley with a red moustache and a red hat in the style of <s0><s1>
  output:
    url: image-23.png
- text: a yellow emoticion singing into a microphone in the style of <s0><s1>
  output:
    url: image-24.png
- text: dora the explorer emoji sticker in the style of <s0><s1>
  output:
    url: image-25.png
- text: optimum - a free online tool for managing your finances in the style of <s0><s1>
  output:
    url: image-26.png
- text: a yellow emoticion with a heart on it in the style of <s0><s1>
  output:
    url: image-27.png
- text: a yellow smiley face with confetti falling from it in the style of <s0><s1>
  output:
    url: image-28.png
- text: a yellow emoticitor with a hat and a wand in the style of <s0><s1>
  output:
    url: image-29.png
- text: a yellow emoticion with sunglasses and a black background in the style of
    <s0><s1>
  output:
    url: image-30.png
- text: a yellow emoticion with wine in his hand in the style of <s0><s1>
  output:
    url: image-31.png
- text: a smiley face with a book and a heart in the style of <s0><s1>
  output:
    url: image-32.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: in the style of <s0><s1>
license: openrail++
---

# SDXL LoRA DreamBooth - blanchon/huggingface-brand-universe

<Gallery />

## Model description

### These are blanchon/huggingface-brand-universe LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.

## Download model

### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke

- **LoRA**: download **[`huggingface-brand-universe.safetensors` here 💾](/blanchon/huggingface-brand-universe/blob/main/huggingface-brand-universe.safetensors)**.
    - Place it on your `models/Lora` folder.
    - On AUTOMATIC1111, load the LoRA by adding `<lora:huggingface-brand-universe:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
- *Embeddings*: download **[`huggingface-brand-universe_emb.safetensors` here 💾](/blanchon/huggingface-brand-universe/blob/main/huggingface-brand-universe_emb.safetensors)**.
    - Place it on it on your `embeddings` folder
    - Use it by adding `huggingface-brand-universe_emb` to your prompt. For example, `in the style of huggingface-brand-universe_emb`
    (you need both the LoRA and the embeddings as they were trained together for this LoRA)
    

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch
from huggingface_hub import hf_hub_download
from safetensors.torch import load_file
        
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('blanchon/huggingface-brand-universe', weight_name='pytorch_lora_weights.safetensors')
embedding_path = hf_hub_download(repo_id='blanchon/huggingface-brand-universe', filename='huggingface-brand-universe_emb.safetensors' repo_type="model")
state_dict = load_file(embedding_path)
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
        
image = pipeline('in the style of <s0><s1>').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)

## Trigger words

To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:

to trigger concept `TOK` → use `<s0><s1>` in your prompt 



## Details
All [Files & versions](/blanchon/huggingface-brand-universe/tree/main).

The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).

LoRA for the text encoder was enabled. False.

Pivotal tuning was enabled: True.

Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.